AN INTELLIGENT DEEP LEARNING FRAMEWORK FOR IRIS DISEASE DETECTION USING LSTM AND RNN

Special Issue - Innovative Commerce: Bridging Business and Computer Applications (ICBBCA-2026) |PG Department of Commerce with Computer Applications, Mannar Thirumalai Naicker College, Madurai – March 2026| International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Glaucoma is one of the leading causes of irreversible blindness worldwide, often progressing silently until significant vision loss has occurred. Early and accurate detection of glaucoma and related iris diseases is therefore critical for effective clinical intervention. This paper proposes a novel deep learning approach based on Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) architectures for the automated detection and classification of iris diseases, with a particular focus on glaucoma. The proposed model, termed IrisLSTM-Net, leverages sequential feature extraction from retinal and iris image data to capture both spatial and temporal patterns associated with disease progression. The framework integrates image preprocessing, optic disc segmentation, and sequential classification to achieve high diagnostic accuracy. Experiments conducted on benchmark ophthalmic datasets demonstrate that the proposed IrisLSTM-Net model achieves a classification accuracy of 96.4%, outperforming existing convolutional neural network-based methods. This study provides a comprehensive analysis of how LSTM/RNN-based deep learning techniques can significantly improve the iris disease detection pipeline, reduce diagnostic errors, and support ophthalmologists in clinical decision-making.

References

1. Joshi, G. D., Sivaswamy, J., & Krishnadas, S. R. (2011). Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment. IEEE Transactions on Medical Imaging, 30(6), 1192–1205.
2. Fumero, F., Alayón, S., Sanchez, J. L., Sigut, J., & Gonzalez-Hernandez, M. (2011). RIM-ONE: An open retinal image database for optic nerve evaluation. 24th International Symposium on Computer-Based Medical Systems (CBMS), pp. 1–6.
3. Gu, Z., Cheng, J., Fu, H., Zhou, K., Hao, H., Zhao, Y., & Liu, J. (2019). CE-Net: Context encoder network for 2D medical image segmentation. IEEE Transactions on Medical Imaging, 38(10), 2281–2292.
4. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
5. Lipton, Z. C., Kale, D. C., Elkan, C., & Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677.
6. Sivaswamy, J., Krishnadas, S. R., Joshi, G. D., Jain, M., & Tabish, A. U. S. (2014). Drishti-GS: Retinal image dataset for optic nerve head (ONH) segmentation. IEEE International Symposium on Biomedical Imaging (ISBI), pp. 53–56.

Keywords

Iris disease detection, glaucoma, deep learning, LSTM, RNN, IrisLSTM-Net, optic disc segmentation, retinal image analysis, sequential classification.